-
Notifications
You must be signed in to change notification settings - Fork 55
Pull requests: NVIDIA/Fuser
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Stream Lowering] second milestone: collective-based comm+compute pipelines
#4252
opened Apr 15, 2025 by
samnordmann
•
Draft
Create short-circuit in persistent outer for-loop to minimize cost of wave quantization.
Matmuls
#4249
opened Apr 14, 2025 by
rdspring1
Loading…
Enable TensorIndexer with the combined scheduler tests
idmodel
#4245
opened Apr 12, 2025 by
naoyam
Loading…
Add support for 2d grid swizzle in hopper matmul scheduler.
Matmuls
#4243
opened Apr 11, 2025 by
rdspring1
Loading…
warp specializied tma persistent kernel, step-2, use TMA load
#4240
opened Apr 11, 2025 by
liqiangxl
Loading…
InsertReshardingsPass decomposes matmul/linear+ReduceScatter.
#4239
opened Apr 11, 2025 by
wujingyue
Loading…
check ID coverage for reference_tv in reduction scheduler
#4223
opened Apr 10, 2025 by
jjsjann123
•
Draft
2 tasks done
Optimize mbarrier placement and enable register sharing with persistent matmul scheduler
Matmuls
#4221
opened Apr 9, 2025 by
rdspring1
Loading…
Create Statement, Expr, and Val bindings
Direct Bindings
Python extension with direct mapping to NvFuser CPP objects.
Python API
Issues related to the Python API
#4157
opened Mar 30, 2025 by
rdspring1
Loading…
Create direct_bindings_api extension
Direct Bindings
Python extension with direct mapping to NvFuser CPP objects.
Python API
Issues related to the Python API
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.